Remove buggy get_test_program and refine c++ reader demo

Author: JiayiFeng

python/paddle/fluid/io.py

@@ -789,101 +789,3 @@ def get_parameter_value_by_name(name, executor, program=None):
         program = default_main_program()
     var = program.global_block().var(name)
     return get_parameter_value(var, executor)
-
-
-def get_test_program(filelist, program=None, startup_program=None):
-    """
-    Transpile current train program to a program to read test dataset
-    if the program is using reader ops like "open_files_op".
-    """
-
-    def _copy_reader_var_(block, var, new_name=None):
-        if new_name == None:
-            new_name = var.name
-        new_var = block.create_var(
-            name=str(new_name), type=core.VarDesc.VarType.READER)
-        new_var.desc.set_shapes(var.desc.shapes())
-        new_var.desc.set_dtypes(var.desc.dtypes())
-        new_var.persistable = True
-        return new_var
-
-    def _get_test_reader_name(train_reader_name):
-        return train_reader_name + "_test"
-
-    def _is_reader_op(op):
-        block = op.block
-        if "Out" in op.output_names:
-            reader_out = block.vars[op.output("Out")[0]]
-            if reader_out.type == core.VarDesc.VarType.READER:
-                return True
-        return False
-
-    if program == None:
-        program = default_main_program()
-    if startup_program == None:
-        startup_program = default_startup_program()
-    startup_block = startup_program.global_block()
-
-    # 1. find out the orignal reader var name
-    startup_reader_op_list = []
-
-    for op in startup_block.ops:
-        if _is_reader_op(op):
-            startup_reader_op_list.append(op)
-
-    if len(startup_reader_op_list) == 0:
-        return program
-
-    root_reader_op = startup_reader_op_list[0]
-    train_test_reader_map = {}
-    # 2. add operators to startup to read open and read test data files
-    for op in startup_reader_op_list:
-        assert (len(op.output("Out")) == 1)
-        train_reader_name = op.output("Out")[0]
-        train_reader = startup_block.vars[train_reader_name]
-        test_reader = _copy_reader_var_(
-            startup_block,
-            train_reader,
-            new_name=_get_test_reader_name(train_reader_name))
-        train_test_reader_map[train_reader.name] = test_reader
-
-        test_op_inputs = {}
-        for name in op.input_names:
-            train_arg_names = op.input(name)
-            test_arg_vars = []
-            for arg_name in train_arg_names:
-                arg_var = train_test_reader_map[
-                    arg_name] if name == "UnderlyingReader" else startup_block.vars[
-                        arg_name]
-                test_arg_vars.append(arg_var)
-            test_op_inputs[name] = test_arg_vars
-
-        test_op = startup_block.append_op(
-            type=op.type,
-            inputs=test_op_inputs,
-            outputs={'Out': [test_reader]},
-            attrs=op.attrs)
-        # root reader op's filelist attr for read test files
-        if op.type == root_reader_op.type:
-            test_op.set_attr("file_names", filelist)
-        if op.type == "create_multi_pass_reader":
-            test_op.set_attr("pass_num", 1)
-
-    # 3. rename reader vars in inference program to different name
-    #    to avoid read from train data.
-    main_block = program.global_block()
-    for var in main_block.vars.values():
-        if var.type == core.VarDesc.VarType.READER:
-            main_block.rename_var(
-                str(var.name), str(_get_test_reader_name(var.name)))
-
-    for op in main_block.ops:
-        if op.type == root_reader_op.type:
-            test_op.set_attr("file_names", filelist)
-        if op.type == "create_multi_pass_reader":
-            test_op.set_attr("pass_num", 1)
-
-    startup_program.sync_with_cpp()
-    program.sync_with_cpp()
-
-    return program

python/paddle/fluid/tests/demo/text_classification/convert_data_to_recordio.py

@@ -31,8 +31,12 @@ def load_vocab(filename):
 
 
 # load word dict with paddle inner function
-word_dict = load_vocab(sys.argv[1])
-word_dict["<unk>"] = len(word_dict)
+if len(sys.argv) > 1:
+    word_dict = load_vocab(sys.argv[1])
+    word_dict["<unk>"] = len(word_dict)
+else:
+    word_dict = paddle.dataset.imdb.word_dict()
+
 print "Dict dim = ", len(word_dict)
 
 # input text data

python/paddle/fluid/tests/demo/text_classification/train.py

@@ -19,7 +19,7 @@
 TRAIN_FILES = ['train.recordio']
 TEST_FILES = ['test.recordio']
 
-DICT_DIM = 89528
+DICT_DIM = 5147
 
 # embedding dim
 emb_dim = 128
@@ -33,33 +33,24 @@
 # class num
 class_dim = 2
 
+# epoch num
+epoch_num = 10
 
-def network_cfg(is_train, pass_num=100):
-    with fluid.unique_name.guard():
-        train_file_obj = fluid.layers.open_files(
-            filenames=TRAIN_FILES,
-            pass_num=pass_num,
-            shapes=[[-1, 1], [-1, 1]],
-            lod_levels=[1, 0],
-            dtypes=['int64', 'int64'],
-            thread_num=1)
-
-        test_file_obj = fluid.layers.open_files(
-            filenames=TEST_FILES,
-            pass_num=1,
-            shapes=[[-1, 1], [-1, 1]],
-            lod_levels=[1, 0],
-            dtypes=['int64', 'int64'],
-            thread_num=1)
 
-        if is_train:
-            file_obj = fluid.layers.shuffle(train_file_obj, buffer_size=1000)
-        else:
-            file_obj = test_file_obj
+def build_program(is_train):
+    file_obj_handle = fluid.layers.io.open_files(
+        filenames=TRAIN_FILES if is_train else TEST_FILES,
+        shapes=[[-1, 1], [-1, 1]],
+        lod_levels=[1, 0],
+        dtypes=['int64', 'int64'],
+        thread_num=1)
+    if is_train:
+        file_obj = fluid.layers.io.shuffle(file_obj_handle, buffer_size=1000)
+    else:
+        file_obj = file_obj_handle
+    file_obj = fluid.layers.io.double_buffer(file_obj)
 
-        file_obj = fluid.layers.double_buffer(
-            file_obj,
-            name="train_double_buffer" if is_train else 'test_double_buffer')
+    with fluid.unique_name.guard():
 
         data, label = fluid.layers.read_file(file_obj)
 
@@ -90,58 +81,64 @@ def network_cfg(is_train, pass_num=100):
 
         if is_train:
             # SGD optimizer
-            sgd_optimizer = fluid.optimizer.Adagrad(learning_rate=0.01)
+            sgd_optimizer = fluid.optimizer.Adagrad(learning_rate=0.001)
             sgd_optimizer.minimize(avg_cost)
 
-        return {
-            'loss': avg_cost,
-            'log': [avg_cost, acc],
-            'file': train_file_obj if is_train else test_file_obj
-        }
+    return {'loss': avg_cost, 'log': [avg_cost, acc], 'file': file_obj_handle}
 
 
 def main():
     train = fluid.Program()
     startup = fluid.Program()
+    test = fluid.Program()
 
     with fluid.program_guard(train, startup):
-        train_args = network_cfg(is_train=True)
-
-    test = fluid.Program()
+        train_args = build_program(is_train=True)
 
-    with fluid.program_guard(test, fluid.Program()):
-        test_args = network_cfg(is_train=False)
+    with fluid.program_guard(test, startup):
+        test_args = build_program(is_train=False)
 
+    use_cuda = fluid.core.is_compiled_with_cuda()
     # startup
-    place = fluid.CUDAPlace(0)
+    place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
     exe = fluid.Executor(place=place)
     exe.run(startup)
 
     train_exe = fluid.ParallelExecutor(
-        use_cuda=True, loss_name=train_args['loss'].name, main_program=train)
+        use_cuda=use_cuda,
+        loss_name=train_args['loss'].name,
+        main_program=train)
+    test_exe = fluid.ParallelExecutor(
+        use_cuda=use_cuda, main_program=test, share_vars_from=train_exe)
 
     fetch_var_list = [var.name for var in train_args['log']]
-    for i in xrange(sys.maxint):
-        result = map(numpy.array,
-                     train_exe.run(fetch_list=fetch_var_list
-                                   if i % 1000 == 0 else []))
-        if len(result) != 0:
-            print 'Train: ', result
-
-        if i % 1000 == 0:
-            test_exe = fluid.ParallelExecutor(
-                use_cuda=True, main_program=test, share_vars_from=train_exe)
-            loss = []
-            acc = []
-            try:
-                while True:
-                    loss_np, acc_np = map(
-                        numpy.array, test_exe.run(fetch_list=fetch_var_list))
-                    loss.append(loss_np[0])
-                    acc.append(acc_np[0])
-            except:
-                test_args['file'].reset()
-                print 'TEST: ', numpy.mean(loss), numpy.mean(acc)
+    for epoch_id in range(epoch_num):
+        # train
+        try:
+            batch_id = 0
+            while True:
+                result = map(numpy.array,
+                             train_exe.run(fetch_list=fetch_var_list
+                                           if batch_id % 10 == 0 else []))
+                if len(result) != 0:
+                    print 'Train loss: ', result
+                batch_id += 1
+        except fluid.core.EOFException:
+            print 'End of epoch', epoch_id
+            train_args['file'].reset()
+
+        # test
+        loss = []
+        acc = []
+        try:
+            while True:
+                loss_np, acc_np = map(numpy.array,
+                                      test_exe.run(fetch_list=fetch_var_list))
+                loss.append(loss_np[0])
+                acc.append(acc_np[0])
+        except:
+            test_args['file'].reset()
+            print 'TEST: ', numpy.mean(loss), numpy.mean(acc)
 
 
 if __name__ == '__main__':